Research map / Reinforcement learning / MDPs and planning
Inverse Reinforcement Learning with the Average Reward Criterion
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| SPMD instead of SAC | RL agent · MuJoCo Humanoid | average return: 6923 -> 10249 | Helped |
| SPMD instead of SAC | RL agent · MuJoCo Walker | average return: 6115 -> 4454 | Hurt |
| SPMD instead of SAC | RL agent · MuJoCo Hopper | average return: 3876 -> 3619 | Hurt |
| SPMD instead of SAC | RL agent · MuJoCo Ant | average return: 5118 -> 5230 | No clear effect |
| SPMD instead of SAC | RL agent · MuJoCo Half-Cheetah | average return: 13300 -> 13025 | No clear effect |
| IPMD instead of f-IRL | IRL agent · MuJoCo Hopper | average return: 3083 -> 3564 | Helped |
| IPMD instead of f-IRL | IRL agent · MuJoCo Humanoid | average return: 3580 -> 7379 | Helped |
| IPMD instead of f-IRL | IRL agent · MuJoCo Ant | average return: 5460 -> 4053 | Hurt |
| IPMD instead of IQ-Learn | IRL agent · MuJoCo Half-Cheetah | average return: 9132 -> 12634 | Helped |
| IPMD instead of IQ-Learn on reward recovery | IRL agent · Pendulum and LunarLanderContinuous | span seminorm of reward error | Helped |
Closest papers by meaning
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.92)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.92)
- Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms (ICML 2024 · similarity 0.90)
- How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach (NeurIPS 2024 · similarity 0.90)
- A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning (NeurIPS 2026 · similarity 0.90)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.